vh/esh-pfi-infrastructure
1
0
Fork 0
Code Issues 7 Pull Requests Actions Packages Projects Releases Wiki Activity

rename: pull-hf-model.yaml → pull-hf-repo.yaml

Browse Source 
Playbook handles models, datasets, and spaces (via --var repo_type=...)
since 3025d49 — the "-model" suffix was misleading. Renaming to match
actual scope.

Updates the single in-repo reference (changelog comment in
stacks/llama-swap/conf/config.yaml). config.yaml was scp'd to ana-ml2;
no docker compose restart needed (comment-only).
This commit is contained in:
vh
2026-05-13 18:33:22 -07:00
parent 3025d4930a
commit 662a73ee0e
2 changed files with 4 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files
playbooks/pull-hf-model.yaml → playbooks/pull-hf-repo.yaml
+3 -3
View File
@@ -16,16 +16,16 @@
# Usage:
#
# # Full repo (e.g. safetensors for later AWQ quant + vLLM serving):
# scripts/elway ana-ml2 --playbook playbooks/pull-hf-model.yaml \
# scripts/elway ana-ml2 --playbook playbooks/pull-hf-repo.yaml \
# --var hf_repo=Skywork/Skywork-Reward-V2-Llama-3.1-8B
#
# # Single quant pattern (e.g. one GGUF for llama-swap):
# scripts/elway ana-ml2 --playbook playbooks/pull-hf-model.yaml \
# scripts/elway ana-ml2 --playbook playbooks/pull-hf-repo.yaml \
# --var hf_repo=mradermacher/Selene-1-Mini-Llama-3.1-8B-GGUF \
# --var allow_patterns='*Q6_K*'
#
# # Dataset (preference data, eval set, etc.):
# scripts/elway ana-ml2 --playbook playbooks/pull-hf-model.yaml \
# scripts/elway ana-ml2 --playbook playbooks/pull-hf-repo.yaml \
# --var hf_repo=Skywork/Skywork-Reward-Preference-80K-v0.2 \
# --var repo_type=dataset
#